/sequential-thinking
Step-by-step thinking for complex problems. Trigger with "think step by step", "reason through this", "analyze logically", "solve gradually". Uses Sequential Thinking MCP.
$ npx -y skills add wasabeef/claude-code-cookbook --skill sequential-thinking --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/sequential-thinking
Context preview
The summary Claude sees to decide when to auto-load this skill.
Step-by-step thinking for complex problems. Trigger with "think step by step", "reason through this", "analyze logically", "solve gradually". Uses Sequential Thinking MCP.
SKILL.md
sequential-thinking.SKILL.mddescription: 'Step-by-step thinking for complex problems. Trigger with "think step by step", "reason through this", "analyze logically", "solve gradually". Uses Sequential Thinking MCP.'
allowed-tools:
- mcp__sequential-thinking__create_or_continue_thinking
Step-by-step thinking for complex problems
Solve complex problems step-by-step through a dynamic, iterative thinking process. This flexible approach allows for course corrections and revisions during the thinking process.
Usage
# Request Claude to think sequentially
"Analyze [task] using sequential-thinking"
Basic Examples
# Algorithm design
"Design an efficient caching strategy using sequential-thinking"
# Problem solving
"Solve database performance issues using sequential-thinking"
# Design review
"Examine real-time notification system design using sequential-thinking"
Collaboration with Claude
# Complex implementation strategy
"Examine authentication system implementation strategy using sequential-thinking. Consider OAuth2, JWT, and session management"
# Bug cause analysis
"Analyze memory leak causes using sequential-thinking. Include code review and profiling results"
# Refactoring strategy
cat src/complex_module.js
"Develop a refactoring strategy for this module using sequential-thinking"
# Technology selection
"Analyze front-end framework selection using sequential-thinking. Consider project requirements and constraints"
Thinking Process
1. **Initial Analysis** - Basic understanding and decomposition of the problem 2. **Hypothesis Generation** - Formulate hypotheses for solutions 3. **Verification and Revision** - Verify hypotheses and revise as needed 4. **Branching and Exploration** - Explore multiple solution paths 5. **Integration and Conclusion** - Derive optimal solution
Features
- **Dynamic Adjustment** - Ability to change direction during thinking
- **Hypothesis Testing** - Cycle of forming and testing hypotheses
- **Branching Thinking** - Simultaneously explore multiple thought paths
- **Gradual Refinement** - Step-by-step refinement of solutions
- **Flexibility** - Policy changes based on new information
Detailed Examples
# Complex system design
"Examine e-commerce site microservice design using sequential-thinking. Include order processing, inventory management, and payment integration"
# Security design
"Examine API security design using sequential-thinking. Include authentication, authorization, rate limiting, and audit logging"
# Performance optimization
"Examine large-scale data processing optimization using sequential-thinking. Consider memory usage, processing speed, and scalability"
# Dependency management
"Examine monorepo dependency management strategy using sequential-thinking. Include build time, deployment, and test execution"
Notes
Sequential-thinking is ideal for complex problems that require deepening thought in stages. For simple questions or those with clear answers, use normal question format.
Execution Example
# Usage example
"Examine GraphQL schema design using sequential-thinking"
# Expected behavior
# 1. Initial analysis: Analyze basic requirements for GraphQL schema
# 2. Hypothesis generation: Examine multiple design patterns
# 3. Verification: Verify advantages and disadvantages of each pattern
# 4. Branching: Explore new approaches as needed
# 5. Integration: Propose optimal schema design
Read more
description: 'Step-by-step thinking for complex problems. Trigger with "think step by step", "reason through this", "analyze logically", "solve gradually". Uses Sequential Thinking MCP.' allowed-tools: - mcp__sequential-thinking__create_or_continue_thinking
Step-by-step thinking for complex problems
Solve complex problems step-by-step through a dynamic, iterative thinking process. This flexible approach allows for course corrections and revisions during the thinking process.
Usage
# Request Claude to think sequentially "Analyze [task] using sequential-thinking"
Basic Examples
# Algorithm design "Design an efficient caching strategy using sequential-thinking" # Problem solving "Solve database performance issues using sequential-thinking" # Design review "Examine real-time notification system design using sequential-thinking"
Collaboration with Claude
# Complex implementation strategy "Examine authentication system implementation strategy using sequential-thinking. Consider OAuth2, JWT, and session management" # Bug cause analysis "Analyze memory leak causes using sequential-thinking. Include code review and profiling results" # Refactoring strategy cat src/complex_module.js "Develop a refactoring strategy for this module using sequential-thinking" # Technology selection "Analyze front-end framework selection using sequential-thinking. Consider project requirements and constraints"
Thinking Process
1. **Initial Analysis** - Basic understanding and decomposition of the problem 2. **Hypothesis Generation** - Formulate hypotheses for solutions 3. **Verification and Revision** - Verify hypotheses and revise as needed 4. **Branching and Exploration** - Explore multiple solution paths 5. **Integration and Conclusion** - Derive optimal solution
Features
- **Dynamic Adjustment** - Ability to change direction during thinking
- **Hypothesis Testing** - Cycle of forming and testing hypotheses
- **Branching Thinking** - Simultaneously explore multiple thought paths
- **Gradual Refinement** - Step-by-step refinement of solutions
- **Flexibility** - Policy changes based on new information
Detailed Examples
# Complex system design "Examine e-commerce site microservice design using sequential-thinking. Include order processing, inventory management, and payment integration" # Security design "Examine API security design using sequential-thinking. Include authentication, authorization, rate limiting, and audit logging" # Performance optimization "Examine large-scale data processing optimization using sequential-thinking. Consider memory usage, processing speed, and scalability" # Dependency management "Examine monorepo dependency management strategy using sequential-thinking. Include build time, deployment, and test execution"
Notes
Sequential-thinking is ideal for complex problems that require deepening thought in stages. For simple questions or those with clear answers, use normal question format.
Execution Example
# Usage example "Examine GraphQL schema design using sequential-thinking" # Expected behavior # 1. Initial analysis: Analyze basic requirements for GraphQL schema # 2. Hypothesis generation: Examine multiple design patterns # 3. Verification: Verify advantages and disadvantages of each pattern # 4. Branching: Explore new approaches as needed # 5. Integration: Propose optimal schema design
A collection of commands, roles, and automation scripts for Claude Code. Automate your workflow without unnecessary confirmations, allowing you to focus on what matters.
Repo: wasabeef/claude-code-cookbook
Other skills on claude-code-cookbook.
- /analyze-dependencies
Analyze project dependencies and evaluate architectural health. Trigger with "analyze dependencies", "detect circular dependencies", "architecture issues?", "check module coupling", "find layer violations". Generates dependency matrix, fan-in/fan-out analysis, and prioritized
Open skill - /analyze-performance
Performance analysis based on Core Web Vitals with UX scoring. Trigger with "analyze performance", "improve speed", "check Core Web Vitals", "page speed", "improve LCP", "identify performance issues".
Open skill - /check-fact
Verify information accuracy against codebase and documentation. Trigger with "is this correct?", "fact check", "verify this", "is this accurate?".
Open skill - /check-prompt
Evaluate and improve AI prompt quality. Trigger with "check this prompt", "evaluate prompt quality", "improve this prompt".
Open skill - /commit-message
Generate commit messages from staged changes. Trigger with "suggest commit message", "generate commit message", "what should the commit say?", "write commit message".
Open skill - /context7
Search technical documentation via Context7 MCP. Trigger with "check the docs", "look up documentation", "how to use this library?", "API reference".
Open skill

